Distributed Quantum Computing with QMPI

TL;DR

This paper introduces QMPI, an extension of MPI for distributed quantum computing, along with a performance model SENDQ, to facilitate testing, debugging, and resource estimation of quantum algorithms across interconnected processors.

Contribution

It presents the first high-performance implementation of quantum MPI and a classical-inspired performance model for distributed quantum algorithms, enabling better resource management.

Findings

Quantum MPI prototype demonstrates practical implementation.

SENDQ model effectively predicts distributed quantum algorithm performance.

Optimizations significantly improve algorithm efficiency in the model.

Abstract

Practical applications of quantum computers require millions of physical qubits and it will be challenging for individual quantum processors to reach such qubit numbers. It is therefore timely to investigate the resource requirements of quantum algorithms in a distributed setting, where multiple quantum processors are interconnected by a coherent network. We introduce an extension of the Message Passing Interface (MPI) to enable high-performance implementations of distributed quantum algorithms. In turn, these implementations can be used for testing, debugging, and resource estimation. In addition to a prototype implementation of quantum MPI, we present a performance model for distributed quantum computing, SENDQ. The model is inspired by the classical LogP model, making it useful to inform algorithmic decisions when programming distributed quantum computers. Specifically, we consider several optimizations of two quantum algorithms for problems in physics and chemistry, and we detail their effects on performance in the SENDQ model.